In [54]: runfile('C:/Users/INE4KOR/Desktop/Sep py/complete_model_time_seried_DF.py', wdir='C:/Users/INE4KOR/Desktop/Sep py')

What is the Future Forecast period? 5

Enter dataset: C:\Users\INE4KOR\Desktop\New_data.json

------------------------------------------------------------

Running SKU 1: Key_Sales_3...

Nan less than 60%

BEST ORDER : (1, 0, 1)

RMSE FOR lr: 0

RMSE FOR lasso: 0

RMSE FOR ridge: 0

RMSE FOR en: 0

RMSE FOR huber: 0

RMSE FOR llars: 0

RMSE FOR pa: 0

RMSE FOR cart: 0

RMSE FOR extra: 0

RMSE FOR svmr: 0

RMSE FOR ada: 0

RMSE FOR bag: 0

RMSE FOR rf: 0

RMSE FOR et: 0

RMSE FOR gbm: 0

KEY! AR

RMSE FOR AR: 18

KEY! MA

RMSE FOR MA: 18

KEY! ARMA

RMSE FOR ARMA: 18

KEY! ARIMA

RMSE FOR ARIMA: 18

RMSE FOR SES: 0

RMSE FOR HWES: 0

RMSE FOR naive: 18

RMSE FOR naive_rept: 18

RMSE FOR naive3: 18

RMSE FOR naive6: 18

RMSE FOR naive12: 18

RMSE FOR naive12wa: 18

RMSE FOR sma: 18

RMSE FOR wma: 18

Moving_Average done

Modeling done

RMSE FOR Croston: 5

BEST MODELS : ['pa', 'SES']

ERRORS OF BEST MODELS : 0.0 0.7111112346227481

Running models for ensemble ... 0

RMSE FOR SES: 0

RMSE FOR pa: 0

Running models for ensemble ... 1

RMSE FOR SES: 0

RMSE FOR pa: 0

Running models for ensemble ... 2

RMSE FOR SES: 0

RMSE FOR pa: 0

weight ts: 1.0

weight ml: 1.0

RMSE FOR Ensemble: 0

RMSE FOR naive6wa: 18

Errors:

ML: 0.0

TS: 0.7111112346227481

Ensemble: 0.0

six_naive_WA 18.475208614068023

Best forecast from six naive

Validation Accuracy

[100.0, 100.0, 100.0, 100.0, 100.0]

Forecasts:

ML: [0, 0, 0, 0, 0]

TS: [0, 0, 0, 0, 0]

Ensemble: [0, 0, 0, 0, 0]

Best Forecast [0, 0, 0, 0, 0]

2017-07-01 00:00:00

calculate_forecast_accuracy

------------------------------------------------------------

Running SKU 2: Key_Sales_4...

Nan less than 60%

BEST ORDER : (1, 0, 1)

RMSE FOR lr: 1286

RMSE FOR lr: 1275

RMSE FOR lr: 1601

RMSE FOR lasso: 1286

RMSE FOR lasso: 1275

RMSE FOR lasso: 1601

RMSE FOR ridge: 1286

RMSE FOR ridge: 1275

RMSE FOR ridge: 1601

RMSE FOR en: 1286

RMSE FOR en: 1275

RMSE FOR en: 1601

RMSE FOR huber: 1266

RMSE FOR huber: 811

RMSE FOR huber: 1585

RMSE FOR llars: 1287

RMSE FOR llars: 1276

RMSE FOR llars: 1601

RMSE FOR pa: 2323

RMSE FOR pa: 8147

RMSE FOR pa: 2226

RMSE FOR cart: 1427

RMSE FOR cart: 2521

RMSE FOR cart: 3289

RMSE FOR extra: 772

RMSE FOR extra: 2521

RMSE FOR extra: 3289

RMSE FOR svmr: 1245

RMSE FOR svmr: 1276

RMSE FOR svmr: 1460

RMSE FOR ada: 1159

RMSE FOR ada: 1910

RMSE FOR ada: 1930

RMSE FOR bag: 1346

RMSE FOR bag: 2033

RMSE FOR bag: 2463

RMSE FOR rf: 1351

RMSE FOR rf: 1968

RMSE FOR rf: 2675

RMSE FOR et: 1440

RMSE FOR et: 2217

RMSE FOR et: 3196

RMSE FOR gbm: 1353

RMSE FOR gbm: 3416

RMSE FOR gbm: 2682

KEY! AR

RMSE FOR AR: 2802

RMSE FOR AR: 3103

RMSE FOR AR: 2355

KEY! MA

RMSE FOR MA: 2516

RMSE FOR MA: 2483

RMSE FOR MA: 2844

KEY! ARMA

RMSE FOR ARMA: 3099

RMSE FOR ARMA: 2943

RMSE FOR ARMA: 1777

KEY! ARIMA

RMSE FOR ARIMA: 2516

RMSE FOR ARIMA: 2809

RMSE FOR ARIMA: 2844

RMSE FOR SES: 1298

RMSE FOR SES: 1317

RMSE FOR SES: 1559

RMSE FOR HWES: 1298

RMSE FOR HWES: 1317

RMSE FOR HWES: 1559

RMSE FOR naive: 1818

RMSE FOR naive: 2630

RMSE FOR naive: 4623

RMSE FOR naive_rept: 2216

RMSE FOR naive_rept: 2760

RMSE FOR naive_rept: 3679

RMSE FOR naive3: 3144

RMSE FOR naive3: 2931

RMSE FOR naive3: 3128

RMSE FOR naive6: 3371

RMSE FOR naive6: 3409

RMSE FOR naive6: 1248

RMSE FOR naive12: 2404

RMSE FOR naive12: 2484

RMSE FOR naive12: 1442

RMSE FOR naive12wa: 2953

RMSE FOR naive12wa: 2950

RMSE FOR naive12wa: 1179

RMSE FOR sma: 2516

RMSE FOR sma: 2483

RMSE FOR sma: 2844

RMSE FOR wma: 2410

RMSE FOR wma: 2452

RMSE FOR wma: 2942

Moving_Average done

Modeling done

RMSE FOR Croston: 1818

BEST MODELS : ['huber', 'SES']

ERRORS OF BEST MODELS : 1221.3052514664994 1391.7984033715213

Running models for ensemble ... 0

RMSE FOR SES: 1324

RMSE FOR huber: 1309

Running models for ensemble ... 1

RMSE FOR SES: 1341

RMSE FOR huber: 2043

Running models for ensemble ... 2

RMSE FOR SES: 1614

RMSE FOR huber: 1542

weight ts: 0.5299204103711289

weight ml: 0.47007958962887103

RMSE FOR Ensemble: 1258

RMSE FOR naive6wa: 3175

RMSE FOR naive6wa: 3133

RMSE FOR naive6wa: 798

Errors:

ML: 1221.3052514664994

TS: 1391.7984033715213

Ensemble: 1258.741593815029

six_naive_WA 2369.1142395023844

Best forecast from six naive

Validation Accuracy

[67.203, 54.842, 0, 43.492, 35.084]

Forecasts:

ML: [2915, 2534, 2822, 2748, 2804]

TS: [2944, 2944, 2944, 2944, 2944]

Ensemble: [2930, 2751, 2886, 2851, 2878]

Best Forecast [1738, 2887, 3086, 1236, 3121]

2017-07-01 00:00:00

calculate_forecast_accuracy

------------------------------------------------------------

Running SKU 3: Key_Sales_5...

Nan less than 60%

BEST ORDER : (1, 0, 0)

RMSE FOR lr: 280

RMSE FOR lr: 231

RMSE FOR lr: 304

RMSE FOR lasso: 280

RMSE FOR lasso: 231

RMSE FOR lasso: 304

RMSE FOR ridge: 280

RMSE FOR ridge: 231

RMSE FOR ridge: 304

RMSE FOR en: 280

RMSE FOR en: 231

RMSE FOR en: 304

RMSE FOR huber: 279

RMSE FOR huber: 223

RMSE FOR huber: 350

RMSE FOR llars: 279

RMSE FOR llars: 232

RMSE FOR llars: 298

RMSE FOR pa: 1627

RMSE FOR pa: 238

RMSE FOR pa: 1591

RMSE FOR cart: 385

RMSE FOR cart: 304

RMSE FOR cart: 683

RMSE FOR extra: 385

RMSE FOR extra: 304

RMSE FOR extra: 628

RMSE FOR svmr: 285

RMSE FOR svmr: 266

RMSE FOR svmr: 168

RMSE FOR ada: 269

RMSE FOR ada: 283

RMSE FOR ada: 525

RMSE FOR bag: 275

RMSE FOR bag: 191

RMSE FOR bag: 552

RMSE FOR rf: 392

RMSE FOR rf: 241

RMSE FOR rf: 574

RMSE FOR et: 272

RMSE FOR et: 304

RMSE FOR et: 480

RMSE FOR gbm: 305

RMSE FOR gbm: 496

RMSE FOR gbm: 539

KEY! AR

RMSE FOR AR: 245

RMSE FOR AR: 118

RMSE FOR AR: 200

KEY! MA

RMSE FOR MA: 346

RMSE FOR MA: 301

RMSE FOR MA: 460

KEY! ARMA

RMSE FOR ARMA: 245

RMSE FOR ARMA: 118

RMSE FOR ARMA: 200

KEY! ARIMA

RMSE FOR ARIMA: 200

RMSE FOR ARIMA: 358

RMSE FOR ARIMA: 459

RMSE FOR SES: 338

RMSE FOR SES: 318

RMSE FOR SES: 84

RMSE FOR HWES: 338

RMSE FOR HWES: 318

RMSE FOR HWES: 84

RMSE FOR naive: 203

RMSE FOR naive: 376

RMSE FOR naive: 456

RMSE FOR naive_rept: 246

RMSE FOR naive_rept: 365

RMSE FOR naive_rept: 491

RMSE FOR naive3: 567

RMSE FOR naive3: 453

RMSE FOR naive3: 456

RMSE FOR naive6: 536

RMSE FOR naive6: 297

RMSE FOR naive6: 225

RMSE FOR naive12: 521

RMSE FOR naive12: 399

RMSE FOR naive12: 237

RMSE FOR naive12wa: 598

RMSE FOR naive12wa: 383

RMSE FOR naive12wa: 119

RMSE FOR sma: 346

RMSE FOR sma: 301

RMSE FOR sma: 460

RMSE FOR wma: 314

RMSE FOR wma: 302

RMSE FOR wma: 462

Moving_Average done

Modeling done

RMSE FOR Croston: 358

BEST MODELS : ['svmr', 'AR']

ERRORS OF BEST MODELS : 240.33489952196865 188.33671607404844

Running models for ensemble ... 0

RMSE FOR AR: 359

RMSE FOR svmr: 285

Running models for ensemble ... 1

RMSE FOR AR: 252

RMSE FOR svmr: 266

Running models for ensemble ... 2

RMSE FOR AR: 513

RMSE FOR svmr: 168

weight ts: 0.40119770215377243

weight ml: 0.5988022978462276

RMSE FOR Ensemble: 219

RMSE FOR naive6wa: 481

RMSE FOR naive6wa: 208

RMSE FOR naive6wa: 107

Errors:

ML: 240.33489952196865

TS: 188.33671607404844

Ensemble: 219.69569863791142

six_naive_WA 265.99243310191343

Best forecast from TS

Validation Accuracy

[87.705, 87.879, 6.926, 72.772, 38.889]

Forecasts:

ML: [603, 602, 602, 602, 602]

TS: [435, 412, 398, 382, 367]

Ensemble: [535, 525, 520, 513, 507]

Best Forecast [435, 412, 398, 382, 367]

2017-07-01 00:00:00

calculate_forecast_accuracy

------------------------------------------------------------

Running SKU 4: Key_Sales_6...

Nan less than 60%

BEST ORDER : (12, 0, 0)

RMSE FOR lr: 101

RMSE FOR lr: 97

RMSE FOR lr: 87

RMSE FOR lasso: 101

RMSE FOR lasso: 97

RMSE FOR lasso: 87

RMSE FOR ridge: 101

RMSE FOR ridge: 97

RMSE FOR ridge: 87

RMSE FOR en: 101

RMSE FOR en: 97

RMSE FOR en: 87

RMSE FOR huber: 47

RMSE FOR huber: 54

RMSE FOR llars: 95

RMSE FOR llars: 101

RMSE FOR llars: 92

RMSE FOR pa: 108

RMSE FOR pa: 69

RMSE FOR pa: 73

RMSE FOR cart: 50

RMSE FOR cart: 111

RMSE FOR cart: 214

RMSE FOR extra: 46

RMSE FOR extra: 77

RMSE FOR extra: 79

RMSE FOR svmr: 82

RMSE FOR svmr: 110

RMSE FOR svmr: 124

RMSE FOR ada: 75

RMSE FOR ada: 97

RMSE FOR bag: 83

RMSE FOR bag: 107

RMSE FOR bag: 104

RMSE FOR rf: 89

RMSE FOR rf: 96

RMSE FOR rf: 113

RMSE FOR et: 86

RMSE FOR et: 122

RMSE FOR et: 115

RMSE FOR gbm: 95

RMSE FOR gbm: 113

RMSE FOR gbm: 126

KEY! AR

RMSE FOR AR: 77

RMSE FOR AR: 102

RMSE FOR AR: 83

KEY! MA

RMSE FOR MA: 77

RMSE FOR MA: 102

RMSE FOR MA: 70

KEY! ARMA

RMSE FOR ARMA: 77

RMSE FOR ARMA: 102

RMSE FOR ARMA: 83

KEY! ARIMA

RMSE FOR ARIMA: 76

RMSE FOR ARIMA: 102

RMSE FOR ARIMA: 70

RMSE FOR SES: 41

RMSE FOR SES: 55

RMSE FOR SES: 58

RMSE FOR HWES: 41

RMSE FOR HWES: 55

RMSE FOR HWES: 58

RMSE FOR naive: 49

RMSE FOR naive: 71

RMSE FOR naive: 70

RMSE FOR naive_rept: 61

RMSE FOR naive_rept: 66

RMSE FOR naive_rept: 77

RMSE FOR naive3: 126

RMSE FOR naive3: 100

RMSE FOR naive3: 94

RMSE FOR naive6: 63

RMSE FOR naive6: 59

RMSE FOR naive6: 80

RMSE FOR naive12: 49

RMSE FOR naive12: 71

RMSE FOR naive12: 70

RMSE FOR naive12wa: 68

RMSE FOR naive12wa: 78

RMSE FOR sma: 77

RMSE FOR sma: 102

RMSE FOR sma: 70

RMSE FOR wma: 76

RMSE FOR wma: 103

RMSE FOR wma: 65

Moving_Average done

Modeling done

RMSE FOR Croston: 76

BEST MODELS : ['huber', 'SES']

ERRORS OF BEST MODELS : 50.14984763013127 51.638453657303614

Running models for ensemble ... 0

RMSE FOR SES: 89

RMSE FOR huber: 52

Running models for ensemble ... 1

RMSE FOR SES: 117

RMSE FOR huber: 73

Running models for ensemble ... 2

RMSE FOR SES: 131

RMSE FOR huber: 74

weight ts: 0.3727648397373213

weight ml: 0.6272351602626788

RMSE FOR Ensemble: 41

RMSE FOR naive6wa: 50

RMSE FOR naive6wa: 41

RMSE FOR naive6wa: 55

Errors:

ML: 50.14984763013127

TS: 51.638453657303614

Ensemble: 41.54756310543375

six_naive_WA 48.90675665047154

Best forecast from six naive

Validation Accuracy

[83.871, 80.556, 68.519, 62.179, 32.222]

Forecasts:

ML: [180, 250, 245, 305, 247]

TS: [223, 223, 223, 223, 223]

Ensemble: [196, 239, 236, 274, 238]

Best Forecast [214, 232, 242, 179, 170]

2017-07-01 00:00:00

calculate_forecast_accuracy

------------------------------------------------------------

Running SKU 5: Key_Sales_7...

Nan less than 60%

BEST ORDER : (1, 1, 0)

RMSE FOR lr: 1985

RMSE FOR lr: 2016

RMSE FOR lr: 1861

RMSE FOR lasso: 1985

RMSE FOR lasso: 2016

RMSE FOR lasso: 1861

RMSE FOR ridge: 1985

RMSE FOR ridge: 2016

RMSE FOR ridge: 1861

RMSE FOR en: 1985

RMSE FOR en: 2016

RMSE FOR en: 1861

RMSE FOR huber: 1359

RMSE FOR huber: 1195

RMSE FOR huber: 1225

RMSE FOR llars: 1990

RMSE FOR llars: 2021

RMSE FOR llars: 1866

RMSE FOR pa: 327

RMSE FOR pa: 260

RMSE FOR pa: 167

RMSE FOR cart: 204

RMSE FOR cart: 1923

RMSE FOR cart: 310

RMSE FOR extra: 204

RMSE FOR extra: 1923

RMSE FOR extra: 310

RMSE FOR svmr: 2248

RMSE FOR svmr: 2275

RMSE FOR svmr: 2210

RMSE FOR ada: 1129

RMSE FOR ada: 1779

RMSE FOR ada: 1457

RMSE FOR bag: 595

RMSE FOR bag: 1153

RMSE FOR bag: 425

RMSE FOR rf: 542

RMSE FOR rf: 1155

RMSE FOR rf: 488

RMSE FOR et: 267

RMSE FOR et: 1786

RMSE FOR et: 493

RMSE FOR gbm: 176

RMSE FOR gbm: 1760

RMSE FOR gbm: 234

KEY! AR

RMSE FOR AR: 347

RMSE FOR AR: 247

RMSE FOR AR: 57

KEY! MA

RMSE FOR MA: 1835

RMSE FOR MA: 888

RMSE FOR MA: 421

KEY! ARMA

RMSE FOR ARMA: 347

RMSE FOR ARMA: 247

RMSE FOR ARMA: 57

KEY! ARIMA

RMSE FOR ARIMA: 859

RMSE FOR ARIMA: 165

RMSE FOR ARIMA: 90

RMSE FOR SES: 195

RMSE FOR SES: 183

RMSE FOR SES: 182

RMSE FOR HWES: 195

RMSE FOR HWES: 183

RMSE FOR HWES: 182

RMSE FOR naive: 998

RMSE FOR naive: 168

RMSE FOR naive: 338

RMSE FOR naive_rept: 11220

RMSE FOR naive_rept: 11286

RMSE FOR naive_rept: 11407

RMSE FOR naive3: 2116

RMSE FOR naive3: 1532

RMSE FOR naive3: 655

RMSE FOR naive6: 1153

RMSE FOR naive6: 1949

RMSE FOR naive6: 2408

RMSE FOR naive12: 1149

RMSE FOR naive12: 1355

RMSE FOR naive12: 1310

RMSE FOR naive12wa: 2514

RMSE FOR naive12wa: 2389

RMSE FOR naive12wa: 2246

RMSE FOR sma: 1835

RMSE FOR sma: 888

RMSE FOR sma: 421

RMSE FOR wma: 1768

RMSE FOR wma: 777

RMSE FOR wma: 390

Moving_Average done

Modeling done

RMSE FOR Croston: 2899

BEST MODELS : ['pa', 'SES']

ERRORS OF BEST MODELS : 251.99842237864223 187.175826149877

Running models for ensemble ... 0

RMSE FOR SES: 332

RMSE FOR pa: 409

Running models for ensemble ... 1

RMSE FOR SES: 336

RMSE FOR pa: 319

Running models for ensemble ... 2

RMSE FOR SES: 253

RMSE FOR pa: 2707

weight ts: 0.6513566187092448

weight ml: 0.3486433812907552

RMSE FOR Ensemble: 169

RMSE FOR naive6wa: 1063

RMSE FOR naive6wa: 1703

RMSE FOR naive6wa: 2034

Errors:

ML: 251.99842237864223

TS: 187.175826149877

Ensemble: 169.10824935525764

six_naive_WA 1600.518324471727

Best forecast from six naive

Validation Accuracy

[76.42, 0, 0, 0, 0]

Forecasts:

ML: [279, 104, 0, 0, 0]

TS: [457, 457, 457, 457, 457]

Ensemble: [394, 333, 297, 297, 297]

Best Forecast [299, 536, 404, 218, 403]

2017-07-01 00:00:00

calculate_forecast_accuracy

In [55]: